lifeodyssey/dsh-compressor

lifeodyssey★ 0RustLast synced: 2026-08-15

Open on GitHub

DeepSeek Harness plugin: compress tool output, cut up to 20% of context, without touching the context cache or agent performance.

README excerpt

English 中文 dsh-compressor A slim port of Headroom. Compresses tool output and cuts up to 20% of context, without affecting the model's context cache or agent performance. Install How it works A tool run leaves a long log / JSON / diff. Only a small part of it is useful. This plugin shortens that output before the next turn, keeps the original on disk, leaves the already-sent prefix alone so the cache stays valid, and gives the agent a tool to pull the full context back. Compressor code comes from Headroom. Wired in today: Log / Smart / Text / Search / Diff. The only crushers not wired in yet: - [ ] Code-aware (tree-sitter, source code) - [ ] Kompress (ONNX, long prose) Develop Contributing Open PRs on this repo, not on Headroom. Plugin code is in plugins/dsh-compressor (Node 22+, pnpm): Crushers live in crates/ : One change per PR. Plugin changes need tests; crusher changes need cargo test . Details: CONTRIBUTING.md. This plugin is MIT. crates/headroom- remains Apache-2.0.

View full README on GitHub →
Agentscontext-compressiondeepseekdsh-pluginagent

Category